Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19257
    Prev
    Next
    INDEX
    Explanations

    mentions or instances of the word "sneak" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to sneezing and related actions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.75
    FORM
    -0.72
    HCR
    -0.71
    ãĥĩ
    -0.70
    maxwell
    -0.68
    channelAvailability
    -0.66
    å§«
    -0.65
    ulhu
    -0.65
    66666666
    -0.65
    Grant
    -0.64
    POSITIVE LOGITS
     sne
    1.02
    ez
    0.85
    aker
    0.82
    pe
    0.80
    aky
    0.80
    aks
    0.79
    neys
    0.78
    arers
    0.77
    beck
    0.76
     Sne
    0.74
    Activations Density 0.007%

    No Known Activations